Construction of Machine-Labeled Data for Improving Named Entity Recognition by Transfer Learning

Project Code :TCMAPY303

Objective

In this paper, we propose a method for automatically generating training data and effectively using the generated data to reduce the labeling cost. The effect of our proposed method was verified with two versions of DNN-based named entity recognition (NER) models: bidirectional LSTM-CRF and vanilla BERT. Where the proposed NER systems outperform the baseline systems in both languages without the need for additional manual labeling.

Abstract

Deep neural networks (DNNs) require a large amount of manually labeled training data to make significant achievements. However, manual labeling is laborious and costly. In this study, we propose a method for automatically generating training data and effectively using the generated data to reduce the labeling cost. The generated data (called ‘‘machine-labeled data’’) is generated using a bagging-based bootstrapping approach. However, using the machine-labeled data does not guarantee high performance because of errors in the automatic labeling. In order to reduce the impact of mislabeling, we applied a transfer learning approach. The effect of our proposed method was verified with two versions of DNN-based named entity recognition (NER) models: bidirectional LSTM-CRF and vanilla BERT. We conducted NER tasks in two languages (English and Korean). The proposed method results in average F1 scores of 78.87% (3.9% point improvement) with bidirectional LSTM-CRF and 82.08% (1% point improvement) with BERT on three Korean NER datasets. In English, the performance increased by an average of 0.45% points with the two DNN-based models.

Keywords: Named Entity Recognition, Bootstrapping, Bagging, Transfer Learning, Deep Learning.

NOTE: Without the concern of our team, please don't submit to the college. This Abstract varies based on student requirements.

Block Diagram

Specifications

HARDWARE SPECIFICATIONS:

  • Processor- I3/Intel Processor
  •  RAM- 4GB (min)
  • Hard Disk- 128 GB
  • Key Board-Standard Window
  •  Keyboard. Mouse-Two or Three Button Mouse.
  • Monitor-Any.

SOFTWARE SPECIFICATIONS:

  • Operating System: Windows 7+
  • Technology: Python 3.6+
  •  IDE: PyCharm IDE
  •  Libraries Used: Pandas, NumPy, OpenCV, TensorFlow, Matplotlib.

Learning Outcomes

  • Named entity recognition.
  • Bootstrapping.
  • Bagging.
  • Transfer learning.
  • Deep learning.
  • Importance of PyCharm IDE.
  • How ensemble models works.
  • Process of debugging a code.
  • The problem with imbalanced dataset.
  • Benefits of SMOTE technique.
  • Input and Output modules.
  • How test the project based on user inputs and observe the output.
  • Project Development Skills:
    • Problem analyzing skills.
    • Problem solving skills.
    • Creativity and imaginary skills.
    • Programming skills.
    • Deployment.
    • Testing skills.
    • Debugging skills.
    • Project presentation skills.
    • Thesis writing skills.

Demo Video

mail-banner
call-banner
contact-banner
Request Video

Related Projects

Final year projects